Artificial Analysis TTS leaderboard: Voxtral 3 leads speed at 112.3 chars/s, Eleven v4 tops quality
ArtificialAnlys · x · 2026-10-21
Artificial Analysis published its Text to Speech and Speech to Text leaderboards plus a Speech Arena for voting.
- Speed: Voxtral 3 TTS generates 112.3 chars/s, well ahead of Eleven v4 Turbo (78.1), Simba 3.2 (77.8), Gemini 3.8 Flash TTS (55.3), and Breeze TTS 2 (43.4)
- Pricing: Voxtral 3 TTS costs $13/1M chars — below Gemini 3.8 Flash TTS ($16.5), Breeze TTS 2 ($34), and Eleven v4 Turbo ($40), above Simba 3.2 ($6.6)
- Quality (Arena Elo): Eleven v4 Turbo leads at 1330, followed by Eleven v4 (1328), Qwen-Audio-3.1-TTS-Plus (1298), Sonic 3.6 (1290), and Gemini 3.8 Flash TTS (1279)
More from Multimodal
- This stunning W51A star-forming region image was AI-processed from raw JWST captures — fofrAI · 2026-10-21
- Purify Before You Align: filtering locally predictable info improves diffusion alignment — volokuleshov · 2026-10-21
- Mistral AI launches Voxtral 3, a real-time voice agent stack in 50+ languages — The Decoder · 2026-10-21
- Full AI Virtual Influencer Character Sheet for 'JataJett': Turnarounds, Expressions and Action Modes in One Page — CurieuxExplorer · 2026-10-21
- AI satire video: 'Paris City Tours, 50% off — slightly different experience' — DavidmComfort · 2026-10-21
- AI-Generated Series 'The Sage' Hits Episode 8, Made Entirely with Invideo Agent — Kavanthekid · 2026-10-21